How to use Julia to compute the pearson correlation coefficient with p-value?

Question

I am looking for help to calculate the Pearson correlation coefficient with p-value by using Julia language. The analogous function in Python is scipy.stats.pearson.

The Julia function below only gives me the correlation. Appreciate your help/hint about the p-value part.

using RDatasets, Statistics
iris = dataset("datasets", "iris");
Statistics.cor(iris.SepalLength, iris.SepalWidth)

Answer 1

I do not know about an existing implementation but here is a two-sided test with H0 equal to 0 using Fisher transformation:

using Distributions

cortest(x,y) =
    if length(x) == length(y)
        2 * ccdf(Normal(), atanh(abs(cor(x, y))) * sqrt(length(x) - 3))
    else
        error("x and y have different lengths")
    end

or use the HypothesisTests.jl package, e.g.:

using HypothesisTests

OneSampleZTest(atanh(cor(iris.SepalLength, iris.SepalWidth)),
               1, nrow(iris)-3)

Answer 2

Now you can also use the function pvalue from HypothesisTests, for example:

 using HypothesisTests
 x = [1,2,3]; y = [2,3,5];
 pvalue(CorrelationTest(x,y))

This example returns 0.1210377 which is the same than python's scipy.stats.pearsonr and R's cor.test.